Upload folder using huggingface_hub
Browse files- config.json +28 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +432 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/xlm-v-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"XLMRobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.41.2",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 901629
|
| 28 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f6dd918c36fadd3498b85134f99868826accf3b9dd34e3d6983d0e4e50b640
|
| 3 |
+
size 3114003416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcecf1d62854b12d3769f1047756eda61aca276178c2fa57d2f052e6a69a78e5
|
| 3 |
+
size 6228131858
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a36fedb56c18b8956a1a960fd61eee9346a81b45d97785ce8389eb6293135c9a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ddeb483ab2976b44726760e4177d1f2b2dcb72ebf25afba0c989632df7e861e
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,432 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7947742682321812,
|
| 3 |
+
"best_model_checkpoint": "./XLM-V_64-multi-outputs/checkpoint-15000",
|
| 4 |
+
"epoch": 14.8619957537155,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 21000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7077140835102619,
|
| 13 |
+
"grad_norm": 1.493615746498108,
|
| 14 |
+
"learning_rate": 9.433962264150943e-07,
|
| 15 |
+
"loss": 0.6936,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.7077140835102619,
|
| 20 |
+
"eval_accuracy": 0.5659663447177138,
|
| 21 |
+
"eval_f1": 0.6995657867530498,
|
| 22 |
+
"eval_loss": 0.682445764541626,
|
| 23 |
+
"eval_precision": 0.5400659785037778,
|
| 24 |
+
"eval_recall": 0.9927621283255086,
|
| 25 |
+
"eval_runtime": 57.8197,
|
| 26 |
+
"eval_samples_per_second": 173.695,
|
| 27 |
+
"eval_steps_per_second": 2.715,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.4154281670205238,
|
| 32 |
+
"grad_norm": 3.4982151985168457,
|
| 33 |
+
"learning_rate": 1.8867924528301887e-06,
|
| 34 |
+
"loss": 0.672,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.4154281670205238,
|
| 39 |
+
"eval_accuracy": 0.6204321417903017,
|
| 40 |
+
"eval_f1": 0.7176714560805807,
|
| 41 |
+
"eval_loss": 0.6340225338935852,
|
| 42 |
+
"eval_precision": 0.5774731823599524,
|
| 43 |
+
"eval_recall": 0.9477699530516432,
|
| 44 |
+
"eval_runtime": 57.5505,
|
| 45 |
+
"eval_samples_per_second": 174.508,
|
| 46 |
+
"eval_steps_per_second": 2.728,
|
| 47 |
+
"step": 2000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.1231422505307855,
|
| 51 |
+
"grad_norm": 12.846685409545898,
|
| 52 |
+
"learning_rate": 1.907732634338139e-06,
|
| 53 |
+
"loss": 0.6537,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.1231422505307855,
|
| 58 |
+
"eval_accuracy": 0.6434332370805537,
|
| 59 |
+
"eval_f1": 0.7224676431837557,
|
| 60 |
+
"eval_loss": 0.6225757002830505,
|
| 61 |
+
"eval_precision": 0.5982543960980619,
|
| 62 |
+
"eval_recall": 0.9117762128325508,
|
| 63 |
+
"eval_runtime": 57.5731,
|
| 64 |
+
"eval_samples_per_second": 174.439,
|
| 65 |
+
"eval_steps_per_second": 2.727,
|
| 66 |
+
"step": 3000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.8308563340410475,
|
| 70 |
+
"grad_norm": 4.933294296264648,
|
| 71 |
+
"learning_rate": 1.8028833551769331e-06,
|
| 72 |
+
"loss": 0.6499,
|
| 73 |
+
"step": 4000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.8308563340410475,
|
| 77 |
+
"eval_accuracy": 0.6594643034949716,
|
| 78 |
+
"eval_f1": 0.743858597962852,
|
| 79 |
+
"eval_loss": 0.604403555393219,
|
| 80 |
+
"eval_precision": 0.6026699029126213,
|
| 81 |
+
"eval_recall": 0.9714397496087637,
|
| 82 |
+
"eval_runtime": 57.5924,
|
| 83 |
+
"eval_samples_per_second": 174.381,
|
| 84 |
+
"eval_steps_per_second": 2.726,
|
| 85 |
+
"step": 4000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.538570417551309,
|
| 89 |
+
"grad_norm": 9.257452011108398,
|
| 90 |
+
"learning_rate": 1.6980340760157273e-06,
|
| 91 |
+
"loss": 0.6389,
|
| 92 |
+
"step": 5000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.538570417551309,
|
| 96 |
+
"eval_accuracy": 0.660460021905805,
|
| 97 |
+
"eval_f1": 0.6269146608315098,
|
| 98 |
+
"eval_loss": 0.6047727465629578,
|
| 99 |
+
"eval_precision": 0.7112711022840119,
|
| 100 |
+
"eval_recall": 0.5604460093896714,
|
| 101 |
+
"eval_runtime": 57.6043,
|
| 102 |
+
"eval_samples_per_second": 174.344,
|
| 103 |
+
"eval_steps_per_second": 2.725,
|
| 104 |
+
"step": 5000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.246284501061571,
|
| 108 |
+
"grad_norm": 8.192702293395996,
|
| 109 |
+
"learning_rate": 1.5931847968545215e-06,
|
| 110 |
+
"loss": 0.6187,
|
| 111 |
+
"step": 6000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.246284501061571,
|
| 115 |
+
"eval_accuracy": 0.6978990341531415,
|
| 116 |
+
"eval_f1": 0.7157046476761619,
|
| 117 |
+
"eval_loss": 0.5651090741157532,
|
| 118 |
+
"eval_precision": 0.6868705035971223,
|
| 119 |
+
"eval_recall": 0.7470657276995305,
|
| 120 |
+
"eval_runtime": 57.5852,
|
| 121 |
+
"eval_samples_per_second": 174.402,
|
| 122 |
+
"eval_steps_per_second": 2.726,
|
| 123 |
+
"step": 6000
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.953998584571833,
|
| 127 |
+
"grad_norm": 49.664493560791016,
|
| 128 |
+
"learning_rate": 1.488335517693316e-06,
|
| 129 |
+
"loss": 0.5962,
|
| 130 |
+
"step": 7000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 4.953998584571833,
|
| 134 |
+
"eval_accuracy": 0.7021806233197252,
|
| 135 |
+
"eval_f1": 0.7534009398961168,
|
| 136 |
+
"eval_loss": 0.5552804470062256,
|
| 137 |
+
"eval_precision": 0.6511329628046174,
|
| 138 |
+
"eval_recall": 0.8937793427230047,
|
| 139 |
+
"eval_runtime": 57.4997,
|
| 140 |
+
"eval_samples_per_second": 174.662,
|
| 141 |
+
"eval_steps_per_second": 2.73,
|
| 142 |
+
"step": 7000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 5.661712668082095,
|
| 146 |
+
"grad_norm": 7.591745376586914,
|
| 147 |
+
"learning_rate": 1.38348623853211e-06,
|
| 148 |
+
"loss": 0.5716,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.661712668082095,
|
| 153 |
+
"eval_accuracy": 0.7096485114009758,
|
| 154 |
+
"eval_f1": 0.7601184600197434,
|
| 155 |
+
"eval_loss": 0.5378949046134949,
|
| 156 |
+
"eval_precision": 0.65587734241908,
|
| 157 |
+
"eval_recall": 0.903755868544601,
|
| 158 |
+
"eval_runtime": 57.5168,
|
| 159 |
+
"eval_samples_per_second": 174.61,
|
| 160 |
+
"eval_steps_per_second": 2.73,
|
| 161 |
+
"step": 8000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.369426751592357,
|
| 165 |
+
"grad_norm": 7.424753189086914,
|
| 166 |
+
"learning_rate": 1.2786369593709043e-06,
|
| 167 |
+
"loss": 0.531,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 6.369426751592357,
|
| 172 |
+
"eval_accuracy": 0.7241860001991437,
|
| 173 |
+
"eval_f1": 0.746800731261426,
|
| 174 |
+
"eval_loss": 0.4708074629306793,
|
| 175 |
+
"eval_precision": 0.7009265614275909,
|
| 176 |
+
"eval_recall": 0.7991001564945227,
|
| 177 |
+
"eval_runtime": 57.6158,
|
| 178 |
+
"eval_samples_per_second": 174.31,
|
| 179 |
+
"eval_steps_per_second": 2.725,
|
| 180 |
+
"step": 9000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 7.077140835102618,
|
| 184 |
+
"grad_norm": 9.683096885681152,
|
| 185 |
+
"learning_rate": 1.1737876802096983e-06,
|
| 186 |
+
"loss": 0.4858,
|
| 187 |
+
"step": 10000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 7.077140835102618,
|
| 191 |
+
"eval_accuracy": 0.7385243453151449,
|
| 192 |
+
"eval_f1": 0.7664947536902009,
|
| 193 |
+
"eval_loss": 0.44091591238975525,
|
| 194 |
+
"eval_precision": 0.7026410172807304,
|
| 195 |
+
"eval_recall": 0.843114241001565,
|
| 196 |
+
"eval_runtime": 57.5121,
|
| 197 |
+
"eval_samples_per_second": 174.624,
|
| 198 |
+
"eval_steps_per_second": 2.73,
|
| 199 |
+
"step": 10000
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 7.78485491861288,
|
| 203 |
+
"grad_norm": 25.252531051635742,
|
| 204 |
+
"learning_rate": 1.0689384010484928e-06,
|
| 205 |
+
"loss": 0.4577,
|
| 206 |
+
"step": 11000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 7.78485491861288,
|
| 210 |
+
"eval_accuracy": 0.7428059344817286,
|
| 211 |
+
"eval_f1": 0.7718399434678915,
|
| 212 |
+
"eval_loss": 0.42118868231773376,
|
| 213 |
+
"eval_precision": 0.7036559832501208,
|
| 214 |
+
"eval_recall": 0.8546557120500783,
|
| 215 |
+
"eval_runtime": 57.4963,
|
| 216 |
+
"eval_samples_per_second": 174.672,
|
| 217 |
+
"eval_steps_per_second": 2.731,
|
| 218 |
+
"step": 11000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 8.492569002123142,
|
| 222 |
+
"grad_norm": 9.067980766296387,
|
| 223 |
+
"learning_rate": 9.64089121887287e-07,
|
| 224 |
+
"loss": 0.4404,
|
| 225 |
+
"step": 12000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.492569002123142,
|
| 229 |
+
"eval_accuracy": 0.7539579806830629,
|
| 230 |
+
"eval_f1": 0.7588091752074183,
|
| 231 |
+
"eval_loss": 0.40373048186302185,
|
| 232 |
+
"eval_precision": 0.75725696473797,
|
| 233 |
+
"eval_recall": 0.7603677621283255,
|
| 234 |
+
"eval_runtime": 57.7852,
|
| 235 |
+
"eval_samples_per_second": 173.799,
|
| 236 |
+
"eval_steps_per_second": 2.717,
|
| 237 |
+
"step": 12000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.200283085633403,
|
| 241 |
+
"grad_norm": 6.412005424499512,
|
| 242 |
+
"learning_rate": 8.592398427260812e-07,
|
| 243 |
+
"loss": 0.42,
|
| 244 |
+
"step": 13000
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 9.200283085633403,
|
| 248 |
+
"eval_accuracy": 0.7534601214776461,
|
| 249 |
+
"eval_f1": 0.7862938028655274,
|
| 250 |
+
"eval_loss": 0.394222617149353,
|
| 251 |
+
"eval_precision": 0.7035835650293482,
|
| 252 |
+
"eval_recall": 0.8910406885758998,
|
| 253 |
+
"eval_runtime": 57.6787,
|
| 254 |
+
"eval_samples_per_second": 174.12,
|
| 255 |
+
"eval_steps_per_second": 2.722,
|
| 256 |
+
"step": 13000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 9.907997169143666,
|
| 260 |
+
"grad_norm": 9.248723983764648,
|
| 261 |
+
"learning_rate": 7.543905635648754e-07,
|
| 262 |
+
"loss": 0.4061,
|
| 263 |
+
"step": 14000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.907997169143666,
|
| 267 |
+
"eval_accuracy": 0.7524644030668127,
|
| 268 |
+
"eval_f1": 0.7793752218672346,
|
| 269 |
+
"eval_loss": 0.3883645236492157,
|
| 270 |
+
"eval_precision": 0.7132878492527616,
|
| 271 |
+
"eval_recall": 0.8589593114241002,
|
| 272 |
+
"eval_runtime": 57.5171,
|
| 273 |
+
"eval_samples_per_second": 174.609,
|
| 274 |
+
"eval_steps_per_second": 2.73,
|
| 275 |
+
"step": 14000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 10.615711252653927,
|
| 279 |
+
"grad_norm": 8.524171829223633,
|
| 280 |
+
"learning_rate": 6.495412844036698e-07,
|
| 281 |
+
"loss": 0.4007,
|
| 282 |
+
"step": 15000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 10.615711252653927,
|
| 286 |
+
"eval_accuracy": 0.7528626904311461,
|
| 287 |
+
"eval_f1": 0.7947742682321812,
|
| 288 |
+
"eval_loss": 0.38538095355033875,
|
| 289 |
+
"eval_precision": 0.6883414494414208,
|
| 290 |
+
"eval_recall": 0.9401408450704225,
|
| 291 |
+
"eval_runtime": 57.8102,
|
| 292 |
+
"eval_samples_per_second": 173.724,
|
| 293 |
+
"eval_steps_per_second": 2.716,
|
| 294 |
+
"step": 15000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 11.32342533616419,
|
| 298 |
+
"grad_norm": 4.774406909942627,
|
| 299 |
+
"learning_rate": 5.44692005242464e-07,
|
| 300 |
+
"loss": 0.3936,
|
| 301 |
+
"step": 16000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 11.32342533616419,
|
| 305 |
+
"eval_accuracy": 0.7545554117295629,
|
| 306 |
+
"eval_f1": 0.793083186434987,
|
| 307 |
+
"eval_loss": 0.38386669754981995,
|
| 308 |
+
"eval_precision": 0.6946037347448905,
|
| 309 |
+
"eval_recall": 0.9241001564945227,
|
| 310 |
+
"eval_runtime": 57.8533,
|
| 311 |
+
"eval_samples_per_second": 173.594,
|
| 312 |
+
"eval_steps_per_second": 2.714,
|
| 313 |
+
"step": 16000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 12.031139419674451,
|
| 317 |
+
"grad_norm": 4.318003177642822,
|
| 318 |
+
"learning_rate": 4.398427260812582e-07,
|
| 319 |
+
"loss": 0.3915,
|
| 320 |
+
"step": 17000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 12.031139419674451,
|
| 324 |
+
"eval_accuracy": 0.7562481330279797,
|
| 325 |
+
"eval_f1": 0.7931034482758621,
|
| 326 |
+
"eval_loss": 0.3860309422016144,
|
| 327 |
+
"eval_precision": 0.6982142857142857,
|
| 328 |
+
"eval_recall": 0.9178403755868545,
|
| 329 |
+
"eval_runtime": 57.8089,
|
| 330 |
+
"eval_samples_per_second": 173.728,
|
| 331 |
+
"eval_steps_per_second": 2.716,
|
| 332 |
+
"step": 17000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 12.738853503184714,
|
| 336 |
+
"grad_norm": 15.07564926147461,
|
| 337 |
+
"learning_rate": 3.3499344692005245e-07,
|
| 338 |
+
"loss": 0.3888,
|
| 339 |
+
"step": 18000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 12.738853503184714,
|
| 343 |
+
"eval_accuracy": 0.7568455640744798,
|
| 344 |
+
"eval_f1": 0.7816523605150214,
|
| 345 |
+
"eval_loss": 0.3812848627567291,
|
| 346 |
+
"eval_precision": 0.7198616600790514,
|
| 347 |
+
"eval_recall": 0.8550469483568075,
|
| 348 |
+
"eval_runtime": 57.8126,
|
| 349 |
+
"eval_samples_per_second": 173.716,
|
| 350 |
+
"eval_steps_per_second": 2.716,
|
| 351 |
+
"step": 18000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 13.446567586694975,
|
| 355 |
+
"grad_norm": 10.069337844848633,
|
| 356 |
+
"learning_rate": 2.3014416775884665e-07,
|
| 357 |
+
"loss": 0.3832,
|
| 358 |
+
"step": 19000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 13.446567586694975,
|
| 362 |
+
"eval_accuracy": 0.7569451359155631,
|
| 363 |
+
"eval_f1": 0.7900576244947106,
|
| 364 |
+
"eval_loss": 0.37964996695518494,
|
| 365 |
+
"eval_precision": 0.7049884881043745,
|
| 366 |
+
"eval_recall": 0.8984741784037559,
|
| 367 |
+
"eval_runtime": 57.6196,
|
| 368 |
+
"eval_samples_per_second": 174.298,
|
| 369 |
+
"eval_steps_per_second": 2.725,
|
| 370 |
+
"step": 19000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 14.154281670205236,
|
| 374 |
+
"grad_norm": 8.055023193359375,
|
| 375 |
+
"learning_rate": 1.252948885976409e-07,
|
| 376 |
+
"loss": 0.383,
|
| 377 |
+
"step": 20000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 14.154281670205236,
|
| 381 |
+
"eval_accuracy": 0.7573434232798965,
|
| 382 |
+
"eval_f1": 0.7904016513288037,
|
| 383 |
+
"eval_loss": 0.3802996873855591,
|
| 384 |
+
"eval_precision": 0.7052954719877207,
|
| 385 |
+
"eval_recall": 0.8988654147104851,
|
| 386 |
+
"eval_runtime": 57.777,
|
| 387 |
+
"eval_samples_per_second": 173.824,
|
| 388 |
+
"eval_steps_per_second": 2.717,
|
| 389 |
+
"step": 20000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 14.8619957537155,
|
| 393 |
+
"grad_norm": 2.661689281463623,
|
| 394 |
+
"learning_rate": 2.0445609436435123e-08,
|
| 395 |
+
"loss": 0.3823,
|
| 396 |
+
"step": 21000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 14.8619957537155,
|
| 400 |
+
"eval_accuracy": 0.7576421388031465,
|
| 401 |
+
"eval_f1": 0.7906056434962148,
|
| 402 |
+
"eval_loss": 0.37897399067878723,
|
| 403 |
+
"eval_precision": 0.7056203931203932,
|
| 404 |
+
"eval_recall": 0.8988654147104851,
|
| 405 |
+
"eval_runtime": 57.6891,
|
| 406 |
+
"eval_samples_per_second": 174.088,
|
| 407 |
+
"eval_steps_per_second": 2.721,
|
| 408 |
+
"step": 21000
|
| 409 |
+
}
|
| 410 |
+
],
|
| 411 |
+
"logging_steps": 1000,
|
| 412 |
+
"max_steps": 21195,
|
| 413 |
+
"num_input_tokens_seen": 0,
|
| 414 |
+
"num_train_epochs": 15,
|
| 415 |
+
"save_steps": 1000,
|
| 416 |
+
"stateful_callbacks": {
|
| 417 |
+
"TrainerControl": {
|
| 418 |
+
"args": {
|
| 419 |
+
"should_epoch_stop": false,
|
| 420 |
+
"should_evaluate": false,
|
| 421 |
+
"should_log": false,
|
| 422 |
+
"should_save": true,
|
| 423 |
+
"should_training_stop": false
|
| 424 |
+
},
|
| 425 |
+
"attributes": {}
|
| 426 |
+
}
|
| 427 |
+
},
|
| 428 |
+
"total_flos": 3.173409489802339e+17,
|
| 429 |
+
"train_batch_size": 64,
|
| 430 |
+
"trial_name": null,
|
| 431 |
+
"trial_params": null
|
| 432 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12b63819340b3d7edb21d08f611fa95a9314421ddb7bb063c3cba8c43ccdc949
|
| 3 |
+
size 5048
|